DeepMind's AlphaProof Code formally verified parts of Signal
Original title: A New AI Tool From Google DeepMind Proved the Signal Protocol Is Secure
A four-week proof of concept found no new flaws and correctly flagged known bugs in older versions.
Google DeepMind used a framework called AlphaProof Code to formally verify several cryptographic guarantees of the Signal protocol. The work did not cover the entire Signal mobile app and found no new vulnerabilities in the portions examined. Researchers are releasing the specification and proof. Google declined to disclose the analysis cost or any commercial plans.
Unconfirmed: Google declined to say whether formal verification will become a commercial product, and scaling cost is unknown.
- Signal's CTO said the approach expands earlier verification of smaller code portions.
- WIRED says the same cryptography protects Google Messages and WhatsApp.
- Researchers say agents still need human review at key steps.
- Vendors
- Products
- Signal
- Organizations
- Google DeepMindSignal Foundation
- AI models
- AlphaProof Code
From the original article
3 min read at wired.com
DeepMind researchers were able to formally verify that the widely used encryption protocol works as intended. Their stretch goal? Do the same for “all the software of the world.”
By Lily Hay Newman · wired.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.